# 本文件程序?yàn)榕浜辖滩募皩W(xué)習(xí)進(jìn)度漸進(jìn)進(jìn)行，請(qǐng)按照注釋分段執(zhí)行 # 執(zhí)行時(shí)要注意IDE的當(dāng)前工作過路徑，最好每段重啟控制器一次，輸出結(jié)果更準(zhǔn)確   # Part1: 通過tf.train.Saver類實(shí)現(xiàn)保存和載入神經(jīng)網(wǎng)絡(luò)模型  # 執(zhí)行本段程序時(shí)注意當(dāng)前的工作路徑 import tensorflow as tf  v1 = tf.Variable(tf.constant(1.0, shape=[1]), name="v1") v2 = tf.Variable(tf.constant(2.0, shape=[1]), name="v2") result = v1 + v2  saver = tf.train.Saver()  with tf.Session() as sess:  sess.run(tf.global_variables_initializer())  saver.save(sess, "Model/model.ckpt")   # Part2: 加載TensorFlow模型的方法  import tensorflow as tf  v1 = tf.Variable(tf.constant(1.0, shape=[1]), name="v1") v2 = tf.Variable(tf.constant(2.0, shape=[1]), name="v2") result = v1 + v2  saver = tf.train.Saver()  with tf.Session() as sess:  saver.restore(sess, "./Model/model.ckpt") # 注意此處路徑前添加"./"  print(sess.run(result)) # [ 3.]   # Part3: 若不希望重復(fù)定義計(jì)算圖上的運(yùn)算，可直接加載已經(jīng)持久化的圖  import tensorflow as tf  saver = tf.train.import_meta_graph("Model/model.ckpt.meta")  with tf.Session() as sess:  saver.restore(sess, "./Model/model.ckpt") # 注意路徑寫法  print(sess.run(tf.get_default_graph().get_tensor_by_name("add:0"))) # [ 3.]   # Part4： tf.train.Saver類也支持在保存和加載時(shí)給變量重命名  import tensorflow as tf  # 聲明的變量名稱name與已保存的模型中的變量名稱name不一致 u1 = tf.Variable(tf.constant(1.0, shape=[1]), name="other-v1") u2 = tf.Variable(tf.constant(2.0, shape=[1]), name="other-v2") result = u1 + u2  # 若直接生命Saver類對(duì)象，會(huì)報(bào)錯(cuò)變量找不到 # 使用一個(gè)字典dict重命名變量即可，{"已保存的變量的名稱name": 重命名變量名} # 原來(lái)名稱name為v1的變量現(xiàn)在加載到變量u1（名稱name為other-v1）中 saver = tf.train.Saver({"v1": u1, "v2": u2})  with tf.Session() as sess:  saver.restore(sess, "./Model/model.ckpt")  print(sess.run(result)) # [ 3.]   # Part5: 保存滑動(dòng)平均模型  import tensorflow as tf  v = tf.Variable(0, dtype=tf.float32, name="v") for variables in tf.global_variables():  print(variables.name) # v:0  ema = tf.train.ExponentialMovingAverage(0.99) maintain_averages_op = ema.apply(tf.global_variables()) for variables in tf.global_variables():  print(variables.name) # v:0        # v/ExponentialMovingAverage:0  saver = tf.train.Saver()  with tf.Session() as sess:  sess.run(tf.global_variables_initializer())  sess.run(tf.assign(v, 10))  sess.run(maintain_averages_op)  saver.save(sess, "Model/model_ema.ckpt")  print(sess.run([v, ema.average(v)])) # [10.0, 0.099999905]   # Part6: 通過變量重命名直接讀取變量的滑動(dòng)平均值  import tensorflow as tf  v = tf.Variable(0, dtype=tf.float32, name="v") saver = tf.train.Saver({"v/ExponentialMovingAverage": v})  with tf.Session() as sess:  saver.restore(sess, "./Model/model_ema.ckpt")  print(sess.run(v)) # 0.0999999   # Part7: 通過tf.train.ExponentialMovingAverage的variables_to_restore()函數(shù)獲取變量重命名字典  import tensorflow as tf  v = tf.Variable(0, dtype=tf.float32, name="v") # 注意此處的變量名稱name一定要與已保存的變量名稱一致 ema = tf.train.ExponentialMovingAverage(0.99) print(ema.variables_to_restore()) # {'v/ExponentialMovingAverage': <tf.Variable 'v:0' shape=() dtype=float32_ref>} # 此處的v取自上面變量v的名稱name="v"  saver = tf.train.Saver(ema.variables_to_restore())  with tf.Session() as sess:  saver.restore(sess, "./Model/model_ema.ckpt")  print(sess.run(v)) # 0.0999999   # Part8: 通過convert_variables_to_constants函數(shù)將計(jì)算圖中的變量及其取值通過常量的方式保存于一個(gè)文件中  import tensorflow as tf from tensorflow.python.framework import graph_util  v1 = tf.Variable(tf.constant(1.0, shape=[1]), name="v1") v2 = tf.Variable(tf.constant(2.0, shape=[1]), name="v2") result = v1 + v2  with tf.Session() as sess:  sess.run(tf.global_variables_initializer())  # 導(dǎo)出當(dāng)前計(jì)算圖的GraphDef部分，即從輸入層到輸出層的計(jì)算過程部分  graph_def = tf.get_default_graph().as_graph_def()  output_graph_def = graph_util.convert_variables_to_constants(sess,               graph_def, ['add'])   with tf.gfile.GFile("Model/combined_model.pb", 'wb') as f:   f.write(output_graph_def.SerializeToString())   # Part9: 載入包含變量及其取值的模型  import tensorflow as tf from tensorflow.python.platform import gfile  with tf.Session() as sess:  model_filename = "Model/combined_model.pb"  with gfile.FastGFile(model_filename, 'rb') as f:   graph_def = tf.GraphDef()   graph_def.ParseFromString(f.read())   result = tf.import_graph_def(graph_def, return_elements=["add:0"])  print(sess.run(result)) # [array([ 3.], dtype=float32)]